TY - GEN
T1 - Label Refinement for Noisy Annotation in Weakly Supervised Segmentation
AU - Huang, Ziyi
AU - Liu, Hongshan
AU - Zhang, Haofeng
AU - Xing, Fuyong
AU - Laine, Andrew
AU - Angelini, Elsa
AU - Hendon, Christine
AU - Gan, Yu
N1 - Publisher Copyright:
© 2024 SPIE.
PY - 2024
Y1 - 2024
N2 - Deep learning has revolutionized medical image analysis, promising to significantly improve the precision of diagnoses and therapies through advanced segmentation methods. However, the efficacy of deep neural networks is often compromised by the prevalence of imperfect medical labels, while acquiring large-scale, accurately labeled data remains a prohibitive challenge. To address the imperfect label issue, we introduce a novel learning framework that iteratively optimizes both a neural network and its label set to enhance segmentation accuracy. This framework operates through two steps: initially, it robustly trains on a dataset with label noise, distinguishing between clean and noisy labels, and subsequently, it refines noisy labels based on high-confidence predictions from the robust network. By applying this method, not only is the network trained more effectively on imperfect data, but the dataset is progressively cleaned and expanded. Our evaluations are conducted on retina Optical Coherence Tomography datasets using U-Net and SegNet architectures, and demonstrate substantial improvements in segmentation accuracy and data quality, advancing the capabilities of weakly supervised segmentation in medical imaging.
AB - Deep learning has revolutionized medical image analysis, promising to significantly improve the precision of diagnoses and therapies through advanced segmentation methods. However, the efficacy of deep neural networks is often compromised by the prevalence of imperfect medical labels, while acquiring large-scale, accurately labeled data remains a prohibitive challenge. To address the imperfect label issue, we introduce a novel learning framework that iteratively optimizes both a neural network and its label set to enhance segmentation accuracy. This framework operates through two steps: initially, it robustly trains on a dataset with label noise, distinguishing between clean and noisy labels, and subsequently, it refines noisy labels based on high-confidence predictions from the robust network. By applying this method, not only is the network trained more effectively on imperfect data, but the dataset is progressively cleaned and expanded. Our evaluations are conducted on retina Optical Coherence Tomography datasets using U-Net and SegNet architectures, and demonstrate substantial improvements in segmentation accuracy and data quality, advancing the capabilities of weakly supervised segmentation in medical imaging.
KW - Deep Learning
KW - Image Analysis
KW - Label Refinement
KW - Weakly Supervised Segmentation
UR - http://www.scopus.com/inward/record.url?scp=85193494280&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85193494280&partnerID=8YFLogxK
U2 - 10.1117/12.3006817
DO - 10.1117/12.3006817
M3 - Conference contribution
AN - SCOPUS:85193494280
T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE
BT - Medical Imaging 2024
A2 - Colliot, Olivier
A2 - Mitra, Jhimli
T2 - Medical Imaging 2024: Image Processing
Y2 - 19 February 2024 through 22 February 2024
ER -